{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/swe-bench-multimodal-do-ai-systems-generalize","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","arxiv_id":"2410.03859","date":"2024-10-04","proceeding":null,"authors":["John Yang","Carlos E. Jimenez","Alex L. Zhang","Kilian Lieret","Joyce Yang","Xindi Wu","Ori Press","Niklas Muennighoff","Gabriel Synnaeve","Karthik R. Narasimhan","Diyi Yang","Sida I. Wang","Ofir Press"],"abstract":"Autonomous systems for software engineering are now capable of fixing bugs and developing features. These systems are commonly evaluated on SWE-bench (Jimenez et al., 2024a), which assesses their ability to solve software issues from GitHub repositories. However, SWE-bench uses only Python repositories, with problem statements presented predominantly as text and lacking visual elements such as images. This limited coverage motivates our inquiry into how existing systems might perform on unrepresented software engineering domains (e.g., front-end, game development, DevOps), which use different programming languages and paradigms. Therefore, we propose SWE-bench Multimodal (SWE-bench M), to evaluate systems on their ability to fix bugs in visual, user-facing JavaScript software. SWE-bench M features 617 task instances collected from 17 JavaScript libraries used for web interface design, diagramming, data visualization, syntax highlighting, and interactive mapping. Each SWE-bench M task instance contains at least one image in its problem statement or unit tests. Our analysis finds that top-performing SWE-bench systems struggle with SWE-bench M, revealing limitations in visual problem-solving and cross-language generalization. Lastly, we show that SWE-agent's flexible language-agnostic features enable it to substantially outperform alternatives on SWE-bench M, resolving 12% of task instances compared to 6% for the next best system.","url_abs":"https://arxiv.org/abs/2410.03859v1","url_pdf":"https://arxiv.org/pdf/2410.03859v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"swe-bench-multimodal-do-ai-systems-generalize","repo_url":"https://github.com/princeton-nlp/SWE-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"swe-bench-multimodal-do-ai-systems-generalize","repo_url":"https://github.com/swe-bench/swe-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"swe-bench-multimodal-do-ai-systems-generalize","repo_url":"https://github.com/swe-rebench/swe-bench-fork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"data-visualization","task_name":"Data Visualization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.03859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03859"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/swe-bench/swe-bench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/princeton-nlp/SWE-bench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/swe-rebench/swe-bench-fork","reach":null}],"summary":{"ran_honours":1,"ran_violates":2,"unverified":8},"by_repo_kind":{"listed":{"samples":11,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"89291094a7d258d1","entry":"calc_cost","repo":"swe-bench/swe-bench","repo_kind":"listed","path":"swebench/inference/run_api.py","file_url":"https://github.com/swe-bench/swe-bench/blob/HEAD/swebench/inference/run_api.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89291094a7d258d1"}},{"code_sha256_prefix":"3017ed47ee9aa03f","entry":"is_valid_instance","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/collect/build_dataset.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/collect/build_dataset.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3017ed47ee9aa03f"}},{"code_sha256_prefix":"52e6c783a2835e8d","entry":"is_valid_pull","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/collect/build_dataset.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/collect/build_dataset.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52e6c783a2835e8d"}},{"code_sha256_prefix":"54fb861132b237b4","entry":"ansi_escape","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/utils.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54fb861132b237b4"}},{"code_sha256_prefix":"b01afe3459c7c880","entry":"build_command","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/inference/mini_swe_agent.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/inference/mini_swe_agent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b01afe3459c7c880"}},{"code_sha256_prefix":"c19dc5311c7cc4e3","entry":"default_config","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/inference/mini_swe_agent.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/inference/mini_swe_agent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c19dc5311c7cc4e3"}},{"code_sha256_prefix":"d29992f652056b75","entry":"generate_heredoc_delimiter","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/utils.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d29992f652056b75"}},{"code_sha256_prefix":"41cc57d502ca33b3","entry":"gpt_tokenize","repo":"swe-bench/swe-bench","repo_kind":"listed","path":"swebench/inference/run_api.py","file_url":"https://github.com/swe-bench/swe-bench/blob/HEAD/swebench/inference/run_api.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41cc57d502ca33b3"}},{"code_sha256_prefix":"948a6ecae3b3f105","entry":"is_available","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/inference/mini_swe_agent.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/inference/mini_swe_agent.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"948a6ecae3b3f105"}},{"code_sha256_prefix":"0e0303b3f55803c8","entry":"resolve_dataset","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/cli/_datasets.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/cli/_datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e0303b3f55803c8"}},{"code_sha256_prefix":"b30563cdf459e7cb","entry":"setup_logger","repo":"princeton-nlp/SWE-bench","repo_kind":"listed","path":"swebench/logger.py","file_url":"https://github.com/princeton-nlp/SWE-bench/blob/HEAD/swebench/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b30563cdf459e7cb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}